README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
  - sibyl
datasets:
  - imdb
metrics:
  - accuracy
model-index:
  - name: bert-base-uncased-imdb
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: imdb
          type: imdb
          args: plain_text
        metrics:
          - type: accuracy
            value: 0.91264
            name: Accuracy
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: imdb
          type: imdb
          config: plain_text
          split: test
        metrics:
          - type: accuracy
            value: 0.93036
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjlmYzNkZTNjOTNhZWY0YTg3OTdmYjIwYTY0ZmI5MDUwYjJkNTk5YTY5MDEyYTcyMDMzODlmZjQxZDY1ODUyYiIsInZlcnNpb24iOjF9.h_9Qsgg_byUX13nnnaNPp_mnT9KR6QvB0YvCFxy71UFW3YcsmpNmUTt8COOvEKRotNVStlKGnAnOckcBzRYtDg
          - type: precision
            value: 0.924887449648527
            name: Precision
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTExMGViZWExYmQ3M2Y3Mzc0MTNjYTZmNjcyZWQ4Y2VkYmNkM2E4MTRlMjEyZTlhY2I4NGQ4NDhkMWY3NGFkNyIsInZlcnNpb24iOjF9.XfxxeG40FeIpPiJxjbDEehMoYd-fY0pXO9Ak-abMd6-TLpSehPoeb27TJFxkdYqBGpekqD3QTWd3nQ8OIoEzCw
          - type: recall
            value: 0.9368
            name: Recall
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWZkMTU3ZDFmMGVlZDJlZTYzMzc0MThkYjI5NTg4MTE5ODhhOTdkY2E3ZGJmODUxY2UzZDQ4YjJmMGIyMWZlMCIsInZlcnNpb24iOjF9.oONtL0mKEwKLSigAC2Gvy67PyjNfWSZlP-rcL5CTlj_aGrt4znzsBYN2i0RpDfsTCACuLGAOyaL2cwnpwi2WDw
          - type: auc
            value: 0.9745117632000001
            name: AUC
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTIwMTM5NTcxZmU2MDc2ZjhhZmNkY2ZjMWZlODA1ZTgwYmZjMTA0ZjlmNWM0NGQwNjhjMDI0ZDJjMDVjOTQ0NCIsInZlcnNpb24iOjF9.LGcnjiLWV2A3aNz7qnnq4M__F1uw3ox3HjVptRCFbW9DxpKXstGdtsE6CbvBWpWnGxF_cvyB4ja4ONNYJr2dCw
          - type: f1
            value: 0.930805611859624
            name: F1
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmIzM2M3NGIwNjRhZmZkMTQ1MDgyMTRkMzVlMzg3NDFlYWE2ZGEyOGVmYTdiZTAxYjZlNWJhMjRiYTEwODA0YSIsInZlcnNpb24iOjF9.RCaUiX3VEqGZ8hY-O2eTHq3BAZWlPpUV_Sz9qK3gnrSY6kiv4g-WO_DHeQ0zjnNPYNoYJCWXXsM1LNt3oFv2Aw
          - type: loss
            value: 0.38993313908576965
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzZmMDBhZWVmNmEzZmExNDM4ODY3N2Q5ZjEwMGJhZGNiODhiYzUzM2M2Y2FkZGQwNmJmYWIyM2VjOTE4ZDkzYiIsInZlcnNpb24iOjF9.5zqlGhogErsqwbFZr5FxdFZ3iipRUHWZaoNRRQ10X2N13qoazK24tTRkc0NajCiZfj7uIIio-Itk4SNxCqQZBA

bert-base-uncased-imdb

This model is a fine-tuned version of bert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:

• Loss: 0.4942
• Accuracy: 0.9126

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1546
• training_steps: 15468

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3952	0.65	2000	0.4012	0.86
0.2954	1.29	4000	0.4535	0.892
0.2595	1.94	6000	0.4320	0.892
0.1516	2.59	8000	0.5309	0.896
0.1167	3.23	10000	0.4070	0.928
0.0624	3.88	12000	0.5055	0.908
0.0329	4.52	14000	0.4342	0.92

Framework versions

• Transformers 4.10.2
• Pytorch 1.7.1
• Datasets 1.6.1
• Tokenizers 0.10.3